JP7081057B2 - Smart scale system and how to use it - Google Patents

Description

Mutual reference to related applications This application is a US provisional patent application No. 62 / 863,476 filed on April 19, 2019, and a US provisional patent application No. 62/957 filed on January 4, 2020. , 210 claims priority and interest, each of which is incorporated herein by reference in its entirety.

The present disclosure relates to health products, more specifically smart scale systems and / or smart mat systems.

Consumers are increasingly focusing on health and health-related products. We focus on weight, what we eat, how we stand, and so on. Therefore, there is a need for versatile devices that generate user health-related information.

This disclosure is intended to address these needs and resolve other issues.

Some implementations of the present disclosure disclose methods for determining the normalized weight of a non-static item. Weight data associated with non-static items is received from multiple load cells. The load cell weight of a non-static item is determined based at least in part on the weight data. The load cell weight of the non-static item is received as input to the machine learning algorithm. The normalized weight of the non-static item is generated as the output of the machine learning algorithm.

In some implementations, the machine learning algorithm also receives a category of non-static items as input. In some implementations, the category of non-static items includes people, animals, inanimate objects, or any combination thereof.

In some implementations, the categories of non-static items are cats, dogs, horses, hamsters, guinea pigs, rabbits, chinchillas, mice, rats, parrots, yadkari, ferrets, reptiles, fish, sea monkeys, or any of them. Further includes combinations of.

In some implementations, historical data associated with non-static items is received. Historical data includes historical load cell weight data and historical normalized weight data. Machine learning algorithms are trained using historical data. In some implementations, historical data is associated with other non-static items in the same category. In some implementations, historical data is associated with non-static items in smart scale systems that contain multiple load cells.

In some implementations, multiple load cells are configured to generate weight data depending on the non-static items involved in the smart scale system, which includes multiple load cells. In some implementations, the non-static items involved in the smart scale system are (i) non-static items that stand on the cover layer of the smart scale system, (ii) non-static items that move across the cover layer of the smart scale system. Includes target item or (iii) both.

In some implementations, the pressure data associated with the non-static item is received from the array of pressure sensors. In some implementations, the array of pressure sensors is configured to generate pressure data depending on the non-static items involved in the smart scale system, including the array of pressure sensors.

In some implementations, pressure heatmaps associated with non-static items are generated, at least in part, based on pressure data. In some embodiments, the pressure heatmap represents the foot of the non-static item or the pressure gradient associated with the foot, showing the weight distribution of the non-static item.

In some implementations, the array of pressure sensors is coupled to a mattress of non-static items. Pressure data during sleep sessions for non-static items is received from an array of pressure sensors. The sleep state of a non-static item is determined, at least in part, based on pressure data during the sleep session of the non-static item. In some implementations, the sleep state of a non-static item includes (i) whether the non-static item has a sleep disorder, (ii) the sleep quality of the non-static item, or (iii) both. ..

In some implementations, weight data during a sleep session for non-static items is received from multiple load cells. Changes in the weight of a non-static item during a sleep session are determined, at least in part, based on the weight data of the non-static item during the sleep session.

According to some implementations of the present disclosure, a smart scale system includes a plurality of load cells, a control system, and a memory. The plurality of load cells are coupled to the first side of the substrate. Multiple load cells are configured to generate weight data associated with non-static items. The control system includes one or more processors. Machine-readable instructions are stored in memory. The control system is bound to memory. In some implementations, the memory and control system is coupled to the first side of the board. Any combination of the above methods is performed when the machine executable instruction in memory is executed by at least one of one or more processors in the control system.

In some implementations, the smart scale system also includes a cover layer. In some implementations, the cover layer comprises a sheet of cloth. In some embodiments, the fabric sheet comprises at least two conductive fabric portions separated from each other. In some implementations, the at least two conductive fabric portions are at least 3 inches apart from each other.

In some implementations, the substrate is one or more pieces of glass. In some mounting embodiments, the substrate comprises two pieces of glass that are coupled together via one or more hinges. In some implementations, the memory and control system is coupled to the first side of the board.

In some implementations, the smart scale system further includes multiple rigid feet. In some embodiments, each of the plurality of rigid feet is directly coupled to one of each of the plurality of load cells.

In some implementations, the smart scale system also includes a base cover. The base cover is coupled to the board so that multiple load cells, memory, and control systems are at least partially positioned between the base cover and the board. In some embodiments, the base cover comprises a plurality of openings, each of the plurality of rigid feet projecting at least partially through at least one of the plurality of openings.

In some embodiments, the plurality of load cells comprises a 4x4 array of load cells. The 4x4 array of load cells is an analog-to-digital converter. In some embodiments, the plurality of load cells comprises at least four single load cells, each of the four single load cells being coupled to their respective analog-to-digital converter.

In some embodiments, the smart scale system further comprises an array of pressure sensors coupled to a second opposite side of the substrate. The array of pressure sensors is configured to generate pressure data associated with non-static items.

In some embodiments, the array of pressure sensors comprises a first sheet and a second sheet. In some embodiments, the first sheet comprises a pressure sensitive sheet positioned adjacent to the second sheet. In some mounting embodiments, the pressure sensitive sheet comprises a piezo resistance sheet configured to change its electrical resistance depending on the pressure applied to it.

In some embodiments, the second sheet comprises a plurality of conductive trace patterns. In some embodiments, each of the plurality of conductive trace patterns defines a pressure sensor in an array of pressure sensors. In some embodiments, each of the plurality of conductive trace patterns includes an inner disk and an outer ring. In some implementations, the outer ring is an equilateral polygon or a perfect circle.

According to some embodiments of the present disclosure, a system for determining the normalized weight of a non-static item is disclosed. The system includes a control system configured to implement the method according to any one of claims 1-15.

According to some implementations of the present disclosure, a computer program product comprises an instruction to cause the computer to perform the method according to any one of claims 1-15 when executed by the computer. In some implementations, computer program products are non-temporary computer-readable media.

The above and additional embodiments and implementations of the present disclosure are those of ordinary skill in the art, with reference to the drawings and given the detailed description of the various embodiments and / or implementations provided below which are outlined. Will be revealed to.

The above and other advantages of the present disclosure will become apparent by reading the detailed description below and referring to the drawings.
It is an exemplary block diagram of a smart scale system according to some implementations of the present disclosure. It is an exemplary block diagram of the smart scale system of FIG. 1 according to some other implementations of the present disclosure. It is a top view of the smart scale system by some implementation form of this disclosure. It is a side view of the smart scale system by some implementation form of this disclosure. It is a side view of the smart scale system by some implementation form of this disclosure. FIG. 5 is a front view of a smart mirror of the smart scale system of FIG. 5 according to some implementations of the present disclosure. It is a side view of the smart mirror of the smart scale system of FIG. 5 by some implementation form of this disclosure. A pressure map of the user's foot of a smart scale system according to some implementations of the present disclosure is shown. A temperature map of the user's foot of a smart scale system according to some implementations of the present disclosure is shown. It is a perspective view of the mat of the smart scale system in the 1st configuration by some implementations of this disclosure. FIG. 9 is a perspective view of the mat of FIG. 9 in a second configuration according to some of the embodiments of the present disclosure. FIG. 3 is a cross-sectional view of a mat of a smart scale system according to some embodiments of the present disclosure. It is an exemplary block diagram of a smart scale system according to some implementations of the present disclosure. FIG. 12A is an exemplary block diagram of the pressure sensing system of the smart scale system of FIG. 12A. FIG. 3 is a first partial perspective view of a smart scale system according to some implementations of the present disclosure. FIG. 13A is a second partial perspective view of the smart scale system of FIG. 13A. FIG. 3 is a partial perspective view of a smart scale system according to some implementations of the present disclosure. A pressure sensor for a smart scale system according to some implementations of the present disclosure is shown. The pressure sensing sheet of the smart scale system according to some implementations of the present disclosure is shown. A first layout of a load cell in a smart scale system according to some implementations of the present disclosure is shown. A second layout of the load cell in a smart scale system according to some implementations of the present disclosure is shown. A third layout of the load cell in a smart scale system according to some implementations of the present disclosure is shown. A fourth layout of a load cell in a smart scale system according to some implementations of the present disclosure is shown. A dog on a smart scale system according to some implementations of the present disclosure is shown. A pressure map of two legs of a dog in a smart scale system is shown according to some implementations of the present disclosure. A temperature map of two legs of a dog in a smart scale system according to some implementations of the present disclosure is shown. It is an exemplary block diagram of a smart scale system according to some implementations of the present disclosure. An in-bed smart scale system according to some implementations of the present disclosure is shown. A smart scale system in a shower is shown according to some implementations of the present disclosure. The current in the pressure sensing sheet prior to the vertically applied pressure according to some of the embodiments of the present disclosure is shown. The current of the pressure sensing sheet of FIG. 20A after the vertically applied pressure according to some of the embodiments of the present disclosure is shown. A transimpedance amplifier according to some implementations of the present disclosure is shown. Another transimpedance amplifier according to some implementations of the present disclosure is shown.

Although the present disclosure is susceptible to various modifications and alternative forms, certain embodiments are illustrated in the drawings and are described in detail herein. However, it should be understood that this disclosure is not intended to be limited to the particular form of disclosure. Rather, the present disclosure includes all modifications, equivalents, and alternatives that fall within the spirit and scope of the present disclosure as defined by the appended claims.

According to some embodiments of the present disclosure, a smart scale for a user to stand can determine a user's posture, pressure point, weight, and the like. At least two different types of pressure sensors, CMOS sensors and sensors containing a thin layer of liquid can be used.

The present disclosure is described with reference to the accompanying figures, and similar reference numbers are used throughout the figure to indicate similar or equivalent elements. The figures are not drawn in proportion to the actual size and are provided solely to illustrate the present disclosure. Some aspects of the disclosure are described below with reference to exemplary uses for illustration. Please understand that a number of specific details, relationships, and methods are presented to provide a complete understanding of this disclosure. However, those skilled in the art of related art will readily recognize that the disclosure can be practiced without one or more specific details or in other ways. In other examples, well-known structures or operations are not shown in detail to avoid obscuring the disclosure. This disclosure is not limited by the illustrated order of actions or events, as some actions may occur in different order and / or at the same time as other actions or events. Moreover, not all of the actions or events illustrated are required to implement the methodology according to the present disclosure.

The term "bonded" is defined as connected, whether directly or indirectly through intervening components, and is not necessarily limited to physical connections. The connection can be such that the object is permanently connected or releasable. The term "substantially" is defined to essentially match a particular dimension, shape, or other word that is substantially modified, so that the components do not need to be accurate. For example, "substantially cylindrical" means, for example, "substantially cylindrical" that an object resembles a cylinder, but can deviate from a true cylinder by one or more. The term "preparing" means "including, but not necessarily limited to," and specifically refers to the state of being an unlimited inclusion or component in such described combinations, groups, series, and the like. ..

Aspects of the present disclosure can be implemented using one or more suitable processing devices such as general purpose computer systems. Microprocessors, digital signal processors, microcontrollers, application-specific integrated circuits (ASICs), programmable logic devices (PLDs), field programmable logic devices (FPLDs), field programmable gate arrays (FPGAs), mobile phones and mobile information terminals (PDAs). ) Such as mobile devices, local servers, remote servers, wearable computers, tablet computers and so on.

A memory storage device for one or more processing devices is a machine-readable medium containing one or more instruction sets (eg, software) that embody any one or more of the methodologies or functions described herein. Can include. Instructions can also be transmitted or received over the network via a network transmitter / receiver. A machine-readable medium can be a single medium, but the term "machine-readable medium" refers to a single medium or multiple media (eg, a centralized or distributed database, and a centralized or distributed database) containing one or more instruction sets. / Or related caches and servers) should be interpreted as including. The term "machine-readable medium" can also store, encode, or convey an instruction set to be executed by a machine, causing the machine to execute any one or more of the various implementations of the methodology. , Or can be interpreted as including any medium capable of storing, encoding, or transporting data structures utilized or associated with such an instruction set. Thus, the term "machine-readable medium" can be construed to include, but is not limited to, solid-state memory, optical media, and magnetic media. Random access memory (RAM) or read-only memory (ROM) in the system, or magnetic, optical, or other read and / or other read and / or magnetic, optical, or other read and / or coupled to a floppy disk, hard disk, CD ROM, DVD ROM, flash, or processing device. Various different types of memory storage devices, such as other computer-readable media that are read and / or written from the writing system, can be used for a single memory or multiple memories.

Generally referring to FIG. 1, the smart scale system 100 for determining a user's user profile includes a mat 110, an imaging device 120 (camera, video recorder, etc.), a display device 130, a processor 132, and a memory device 140. Can include. The mat 110 includes a first sensor 112 configured to output pressure data. The imaging device 120 can be configured to generate reproducible image data as one or more images of the user. The memory device 140 can be configured to receive and store pressure data from the first sensor 112 and image data from the imaging device 120. The memory device 140 stores a machine-readable instruction configured to cause the processor 132 to determine that a portion of the user is in contact with the mat 110 based on pressure data, image data, or both. be able to. Processor 132 can further determine the user profile of the user based on pressure data, image data, or both. The user profile includes the posture of the user. The posture of the user can be determined by comparing the pressure data, the image data, or both with one or more predetermined postures stored in the memory device 140. The predetermined posture may be stored in the database 142 of the memory device 140. The processor 132 can also display information associated with the determined user profile on the display device 130. Optionally, the smart scale system 100 includes a power supply 134 and a user interface 136.

In some implementations, the memory device 140 can be configured to cause the processor 132 to determine the user's identity based on pressure data, image data, or both. The determination process can be performed, for example, by a machine learning algorithm. As an example, a user profile includes the shape of a part of the user (eg, feet, hands, etc.), the dimensions of the part of the user, or any combination thereof. In such an example, the display information associated with the determined user profile is a first sign indicating the weight of the user, a second sign indicating the posture of the user, and a third sign indicating the shape of the part of the user. , A fourth sign indicating the dimensions of the user's portion, etc., or any combination thereof.

In some embodiments, the mat 110 includes a second sensor (not shown) configured to output temperature data. In such an implementation, the memory device 140 causes the processor 132 to determine that a portion of the user is in contact with the mat 110 based on pressure data, image data, temperature data, or any combination thereof. Can be further configured. The first sensor 112 may be the same as or different from the second sensor.

In some embodiments, the smart scale system 100 includes a user interface 136. For example, the user interface 136 can be coupled to the display device 130. The user interface 136 can be configured to receive input data associated with the user. As an example, the input data includes the age or gender of the user.

The memory device 140 of the smart scale system 100 can be further configured to cause the processor 132 to determine the wellness plan of the user based on the determined user profile, and the display information associated with the determined user profile is , And thus can include a sign indicating the wellness of the user. For example, a wellness plan is an exercise schedule.

The memory device 140 of the smart scale system 100 also has the processor 132 based on comparing the pressure data, the image data, or both with one or more predetermined orientations stored in the database 142 of the memory device 140. It can be configured to determine the posture score. For example, the posture score may indicate that the user's posture is poor. In some implementations, the memory device 140 determines the posture correction plan associated with the user on the processor 132 based on comparing pressure data, image data, or both with one or more predetermined postures. Can be configured to.

In some embodiments, the display device 130 is coupled to the mat 110. For example, the mat 110 includes one or more LED lights. The processor 132 can be configured to cause the display device 130 to display a shape indicating a position for the user to place his or her hand or foot on the mat 110. It is configured such that the mat 110 is a yoga mat and the smart scale system 100 displays the suggested yoga poses to the user by recommending placement for the user's hands and / or feet. It can be useful in various situations, such as when you are.

In some implementations, the memory device 140 of the smart scale system 100 may be configured to cause the processor 132 to determine the active period based on determining that the user portion is in contact with the mat 110. can. In some such implementations, the smart scale system 100 receives pressure data from the first sensor 112 and image data from the camera 120 during the active period and displays digital information based on the received data. It can further include virtual reality devices (not shown) configured to do so. As an example, the display device 130 can be coupled to a virtual reality device.

In some implementations, one or more components of the smart scale system 100 include, are part of, or are used in combination with an augmented reality system. The augmented reality system can be configured, for example, through an augmented reality display device to indicate how the user should correct his or her posture (eg, the user is in an outline showing the corrected posture). Looking at themselves, then users can try to align their spine with the outline).

In some embodiments, the mat 110 of the smart scale system 100 is configured to be paired with a mobile phone. For example, the display device 130 is coupled to a mobile phone. The mat 110 can be paired with one, two, three, or any number of other mobile phones. The mat 110 can also be paired with one or more different devices. In some other implementations, the mat 110 of the smart scale system 100 operates in stand-alone mode (eg, without a mobile device).

In some implementations, one or more components of the smart scale system 100 include, are part of, or are used in combination with an artificial intelligence system. For example, the artificial intelligence system can be stored in the cloud, at the edge (such as the IoT edge), or in any combination thereof.

The smart scale system 100 includes a mat 110, one or more sensors 112, an imaging device 120, a display device 130, one or more processors 132, one or more memory devices 140, a database 142, a power supply 134, and a user interface 136. Although shown in FIG. 1 as including, an alternative system similar to or similar to the smart scale system 100 can be constructed with more or less components. For example, a first alternative system (not shown) includes mats, pressure sensors, temperature sensors, cameras, display devices, processors, and memory devices.

FIG. 2 illustrates an exemplary implementation of the present disclosure, where the smart scale system 200 is the same as or similar to the smart scale system 100, except that various components can be combined into different devices. ing. For example, the smart scale system 200 includes a mat 110, an imaging device 120, and a mobile device 150. The mat 110 includes a sensor 112, a power supply 134, and a communication module 114. The mobile device 150 includes a processor 132, a memory device 140, a display device 130, a user interface 136, and a communication module 116. The mat 110 can be communicably coupled to the mobile device 150 via the communication modules 114 and 116. Similarly, the imaging device 120 can be communicably coupled to the mobile device 150. Additional or alternative, the imaging device 120 can be directly coupled to the mobile device 150. As another example, the devices can be coupled to each other via Bluetooth® or BLE.

For example, the power supply 134 includes a battery and an energy harvesting element configured to collect energy for charging the battery. The energy harvesting element can be a transducer that is configured to convert thermal energy into electrical energy to charge the battery. In some cases, the transducer can be coupled to a second sensor configured to output temperature data (such as those described above). Alternatively or additionally, the energy harvesting element is an electrical energy for charging the battery with mechanical energy (eg, vibration from someone standing on or exercising on the mat). It can be a transducer configured to convert to.

3 and 4 show a smart scale system 300 including a mat 110 and a camera 120. The mat 110 includes a sensor 112 configured to sense pressure data associated with the user 160. The camera 120 has a field of view α configured to extend to at least a portion of the user 160 and the mat 110. The user 160 can instruct the camera 120 to rotate at an angle in order to acquire various image data of the camera 120 at different angles.

Various components of the smart scale system 100 can be coupled to various devices. In addition to implementations such as the smart scale system 200, the processor 132 and memory device 140 can be coupled to the mat 110 (FIGS. 9 and 10). The display device 130 can be coupled to a mirror (FIGS. 5, 6A, and 6B), a carpet, a mat 110, or a mobile device 150 (FIG. 2).

FIG. 5 shows a smart scale system 400 including a mat 110 and a smart mirror 170. The camera 120 can be coupled to the smart mirror 170. The camera 120 of the smart mirror 170 has a field of view β configured to extend to at least a portion of the user 160 and the mat 110.

FIG. 6A shows a front view of the smart mirror 170 of the smart scale system 400, while FIG. 6B shows a side view of the smart mirror 170. As can be seen in FIG. 6A, the frame surrounds the mirror 172, while the portion of the activated display device 130 can be seen through the mirror 172. FIG. 6B also shows a two-dimensional grid that can be formed by a mirror sensor within a frame used to detect a user's face, head, or other body part. This two-dimensional grid is generally invisible to the user during operation.

FIG. 6B shows the arrangement of a frame with a mirror sensor, a mirror 172, a display device 130, and a camera. In embodiments, the processor 132 and the memory device 140 can be mounted behind the display device 130. In other embodiments, the processor 132 and memory can be located elsewhere within the smart mirror 170, or can be located entirely outside the smart mirror 170. The smart mirror 170 generally includes a display device 130, a camera, and a processor 132, and also includes housing components 174 and 176 that form a protective housing.

In some implementations, the sensor 112 on the mat 110 can be configured to sense pressure data, as illustrated in FIG. 7, which shows the pressure map 166 of the user's feet 162 and 164. The pressure map 166 represents the pressure gradient associated with the user's feet 162, 164. Further, the pressure map 166 shows the user's weight distribution.

Used in combination with or without pressure map 166, pressure data can be used to generate additional information associated with the user. As a first example, in some implementations, the length of the user's foot can be calculated. In addition, in some implementations, the size of the user's shoes can be estimated, at least in part, based on the calculated foot length. As a second example, in some implementations, the profile of the user's foot can be determined. The foot profile can include a choice from high arc, low arc, and medium arc. As a third example, in some implementations, the profile of the user's insole can be determined. In addition, in some implementations, custom insoles may be created for the user (eg, using 3D printing), at least partially based on the profile of the insole.

As shown, the pressure map 166 includes pressure points 167A1, 167A2, 167A3 of the foot 162. The pressure map 166 further includes pressure points 167B1, 167B2, 167B3 of the foot 164. In some implementations, the pressure map 166 can help detect if the user has diabetic feet. Diabetic feet often have fluid pools and / or nerve loss, which can be detected using electrodes (FIGS. 12A-13B) and / or pressure sensors. As a first example, the area of the diabetic foot can rise over time, resulting in an expansion of the pressure map 166 over time. As a second example, the pressure distribution changes over time (eg, the pressure point 167 moves over time and / or expands over time). In some implementations, instead of analyzing pressure data over time, the pressure data of the current user is compared to the pressure data of other users (users with and without diabetic feet). Can be done. In some embodiments, the pressure map 166 may help detect other discomforts and / or illnesses such as joint disease.

In some implementations, the sensor 112 on the mat 110 can be configured to sense temperature data, as illustrated in FIG. 8, which shows the temperature map 168 of the user's feet 162 and 164. The heat from the user can be used to power the battery of the power supply 134, as shown in FIG. 2 of the present disclosure.

With reference to FIGS. 9 and 10, the mat 110 can be flexible, stretchable, or both, as shown in the smart scale system 700. For example, the mat 110 can be configured to move between a generally planar configuration (FIG. 9) and a generally cylindrical configuration (FIG. 10). For example, the power supply 134, the processor 132, and the memory device 140 may have side portions of the mat 110 such that the side portions 190 of the mat 110 remain relatively flat when the mat 110 is rolled into a cylindrical configuration. Can be combined with 190.

In some embodiments, the first sensor 112 may be a CMOS integrated silicone pressure sensor, or a piezoelectric sensor. In some embodiments, the first sensor 112 includes a liquid embedding layer capable of sensing pressure. For example, the first sensor 112 may be a laminated pressure sensor containing a liquid metal embedded elastomer. As best shown in FIG. 11, the smart scale system 800 includes a top layer 180, a bottom layer 182, and an intermediate layer (eg, sensor 112) between the top layer 180 and the bottom layer 182. The top layer 180 can be made of cloth, rubber, or any other suitable material. Similarly, the bottom layer 182 can be made of cloth, rubber, or any other suitable material.

Next, with reference to FIG. 12A, the smart scale system 900 according to some implementations of the present disclosure is shown. The smart scale system 900 has similar reference numbers that are the same as, similar to, or combined with the smart scale systems of FIGS. 1-11 used to specify similar or equivalent components. Is used. In some embodiments, one or more components of the smart scale system 900 form a smart mat, such as a bath mat or yoga mat.

The smart scale system 900 is used to determine a user's normalized weight, among other applications. The smart scale system 900 includes a control system 918, a memory device 940, one or more processors 932, a weight system 902, and a pressure sensing system 904. In some embodiments, the smart scale system 900 further includes a bioimpedance system 906. In some implementations, the smart scale system 900 further includes a communication network 914.

As shown in FIG. 12A, the control system 918 includes one or more processors 932 (hereinafter, processor 932). The control system 918 is generally used to control (eg, operate) various components of the system 900 and / or to analyze the data acquired and / or generated by the components of the system 900. Processor 932 can be a general purpose or special purpose processor or microprocessor. Although one processor 932 is shown in FIG. 12A, the control system 918 can be in any suitable number of processors (eg, one processor, two) that can be in a single housing or located apart from each other. It can include one processor, five processors, ten processors, etc.). The control system 918 is coupled to the mat of the system 900, the housing of one or more load cells 921 of the weight system 902, the housing of one or more of the sensors 912 of the sensing system 904, or any combination thereof. / Or can be positioned. The control system 918 can be centralized (within one such housing) or decentralized (within two or more of such physically distinct housings). In such implementations that include two or more housings containing a control system 918, such housings can be located in close proximity to and / or apart from each other.

The memory device 940 stores machine-readable instructions that can be executed by the processor 932 of the control system 918. The memory device 940 can be any suitable computer readable storage device or medium, such as, for example, a random or serial access memory device, a hard drive, a solid state drive, a flash memory device, and the like. Although one memory device 940 is shown in FIG. 12A, the system 900 may include any suitable number of memory devices 940 (eg, one memory device, two memory devices, five memory devices, ten memory devices, and the like). Can be included. The memory device 940 is in the mat of the system 900, in the housing of one or more load cells 921 of the weight system 902, in the housing of one or more of the sensors 912 of the sensing system 904, and the user interface (eg, mobile phone, smart). It can be coupled and / or positioned within the housing of the mirror) or in any combination thereof. Similar to the control system 918, the memory device 940 can be centralized (within one such housing) or decentralized (within two or more of such physically distinct housings). ..

In some embodiments, the system 900 further includes an electronic interface (such as the user interface 136 of FIGS. 1-2). The electronic interface is configured to receive data (eg, user input data) so that the data can be stored in the memory device 940 and / or analyzed by the processor 932 of the control system 918. The electronic interface communicates one or more components of the system 900 using a wired or wireless connection (eg, on a cellular network using RF communication protocol, WiFI communication protocol, Bluetooth communication protocol, etc.). can do. The electronic interface can include an antenna, a receiver (eg, an RF receiver), a transmitter (eg, an RF transmitter), a transceiver, or any combination thereof. The electronic interface can also include one or more processors and / or one or more memory devices that are the same as or similar to the processor 932 and memory device 940 described herein. In other embodiments, the electronic interface is coupled to or integrated with the control system 918 and / or the memory device 940 (eg, in a housing).

In some embodiments, the weight system 902 of the smart scale system 900 includes a plurality of load cells 921. For example, as shown in FIG. 12A, the weight system 902 includes four of the 4x4 arrays of load cells, namely 922a, 922b, 922c, and 922d. Each of the 4x4 arrays of load cells is coupled to their respective analog-to-digital converter (ADC). For example, the array of load cells 922a is coupled to ADC 924a, the array of load cells 922b is coupled to ADC 924b, the array of load cells 922c is coupled to ADC 924c, and the array of load cells 922d is coupled to ADC 924d.

In some implementations, the pressure sensing system 904 of the smart scale system 900 includes an array of pressure sensors. In some such implementations, the array of pressure sensors comprises a matrix of any suitable number of pressure sensors. As an example, as shown in FIG. 12A, the array of pressure sensors comprises 912a-912f, which is a 3 × 2 matrix of pressure sensors. As another example, the array of pressure sensors includes a 100x70 matrix of pressure sensors. Additional details and / or alternative implementations of the pressure sensing system 904 are discussed with respect to FIGS. 12B, 13A-13B, and their corresponding description. In addition, an exemplary output (eg, heat map) of the pressure sensing system 904 is shown in FIG.

In some embodiments, the control system 918 is configured to receive weight data from the weight system 902 and pressure data from the pressure sensing system 904. Every user has a unique pressure map (eg, fingerprint) generated by the pressure data associated with the user. Based at least in part on the pressure data (received from the pressure sensing system 904) and the registered user data (stored in the memory device 940 and / or transmitted from the communication network 914), the control system 918 is set by the user. , It is configured to determine whether it is a registered user or an unregistered user of the smart scale system 900.

If the user is an unregistered user of the smart scale system, in some implementations the camera is activated based on at least partly the determination that a portion of the user is in contact with the smart scale system. Generate image data. The determination can be made at least in part based on weight data, pressure data, or both. The generated image data is compared with the registered user data, thereby confirming that the user is an unregistered user of the smart scale system.

In some implementations, the plurality of load cells in the weight system 902 are configured to measure only weight up to a certain amount. The pressure sensing system 904 is configured to pick up the task of measuring weight when the user's weight exceeds the amount measurable by the weight system 902. Therefore, in some implementations, the user's load cell weight is determined based on the weight data received. If the load cell weight does not exceed a predetermined threshold, the load cell weight is displayed on the display device as the user's actual weight. When the load cell weight exceeds a predetermined threshold, (i) the weight of the pressure sensor is estimated for the user, at least partially based on the received pressure data, and (ii) the weight of the pressure sensor is the actual weight of the user. Appears on the display device as the weight of.

In some implementations, the user's weight as measured by the weight system is not accurate enough to reflect the user's true weight, and the smart scale system 900 can normalize it. First, the user's load cell weight is determined based on the received weight data. The determined load cell weight is received as the first input of the machine learning algorithm. Further, the reason for the adjustment is received as a second input of the machine learning algorithm. The machine learning algorithm then produces an output that is the user's normalized weight. Further, in some implementations, the user's load cell weight and / or the user's normalized weight and / or the reason for the adjustment is displayed on the display device.

Reasons for adjustment include: (i) whether the user is wearing or undressing (eg, clothing may add weight and different types of clothing may add different weights), ( ii) User's recent toilet usage (eg, weight may increase without defecation), (iii) Time last eaten and / or drank by user (eg, recent intake of food or drink) (May increase weight), (iv) the type of food in the user's last meal (eg, ingestion of carbohydrates and / or sodium may increase water retention), (v) the state of the shower (eg). , If the hair is wet, the weight may increase), or (vi) any combination thereof may be included.

In addition, machine learning algorithms can be trained using historical data. For example, in some implementations, historical data includes historical load cell weight data and historical normalized weight data. Historical data is from other users (eg, registered user data from other users) and / or smart scales (eg from third-party activity trackers associated with the current user, or other activity tracking databases). Can be associated with the current user of the system. In some implementations, machine learning algorithms can be trained using sensor data measured by other sensors in the smart scale system. For example, in some such implementations, the data provided by the plurality of electrodes 944 can be used to determine if the user is wet.

If the user is a registered user of the Smart Scale System 900, the display device is prompted to enter the information associated with the weight data received by the user. Then, in response to the prompt, user information is received. The weight data is modified to output the normalized weight, at least in part, based on the received user information. In addition, in some implementations, the modified weight data is displayed on the displayed device. User information may include information that is the same as or similar to the reasons for adjustment considered herein. Similarly, if the user is a registered user, a machine learning algorithm can be used. Machine learning algorithms can be further or alternatively trained using user-specific data generated by the user of the smart scale system 900 over a period of time.

In some implementations, the bioimpedance system 906 of the smart scale system 900 is configured to generate bioelectrical impedance data associated with the user. The bioelectrical impedance system 906 includes a plurality of electrodes 944 configured to make conductive contact with the user to form one or more closed circuits with the user. For example, as shown in FIG. 12A, the first pair of electrodes 944a, 944b form a first closed circuit with the user (eg, with the user's first foot) and transmit the bioelectrical impedance module 938. It is configured to generate current data to be generated. The second pair of electrodes 944c, 944d form a second closed circuit with the user (eg, with the user's second foot) to generate voltage data transmitted to the bioelectrical impedance module 938. It is configured. Based at least in part on bioelectrical impedance data (including current and voltage data), the control system 918 is configured to determine the user's estimated body composition, such as the user's body fat and muscle mass.

In some embodiments, the communication network 914 of the smart scale system 900 includes a wireless communication module 926 and a pairing button 928. The wireless communication module 926 includes a BLE module and / or a Wi-Fi module. The pairing button 928 can be physical or virtual. In some embodiments, activation of the pairing button 928 allows the control system to transmit data to and / or from the wireless communication module 926. In some embodiments, the pairing button 928 is a wireless button. For example, in some such implementations, the pairing button 928 includes a Near Field Communication (NFC) button.

The smart scale system 900 of FIG. 12A is shown to include a control system 918, a memory device 940, a weight system 902, a pressure sensing system 904, a bioimpedance system 906, and a communication network 914. It can contain more or less components. As an example, in some implementations, the first alternative smart scale system can include a control system, a weight system, and a sensing system. As another example, in some implementations, the second alternative smart scale system can include a control system, a memory device, a weight system, a pressure sensing system, and a display device. As yet another example, in some implementations, the third alternative smart scale system can include a control system, a memory device, a weight system, a pressure sensing system, a bioimpedance system, and a user input module.

Next, with reference to FIG. 12B, an exemplary block diagram of the pressure sensing system 904 according to some embodiments of the present disclosure is shown. In some embodiments, the shift register is configured to multiply the number of available outputs, and the SPDT MUX is a digital control such as a multiplexer in which two possible outputs are selected for each input. A switch, an AO is an operational capacitor, and a multiplexer CD4051 is a multiplexer in which one output is selected for each input. The main goal of the AO and SPDT MUX is to avoid electrical problems common to the sensor matrix, such as crosstalk. The main goal of the shift register and simple MUX is to make the read simpler (thanks to these, the control system requires less inputs and outputs).

In some implementations, the components of the pressure sensing system 904 are coupled to the PCB, which in turn is connected to the control system 918. In some embodiments, the PCB is wired to a copper row sheet (eg, first sheet 1083 in FIGS. 13A and 13B) and a copper column sheet (eg, third sheet 1085 in FIGS. 13A and 13B). ing. In some such implementations, the PCB is positioned between the substrate 1086 and the base cover 1089 (FIGS. 13A and 13B).

Next, referring to FIGS. 13A and 13B, the smart scale system 1000 is shown. The smart scale system 1000 is the same as or similar to the smart scale system 900, with similar reference numbers designated for similar or equivalent elements. That is, FIG. 13A is an exemplary partial exploded view of the smart scale system according to some of the embodiments of the present disclosure, and FIG. 13B is an exemplary partial exploded view of the smart scale system of FIG. 13A according to some of the embodiments of the present disclosure. It is a reverse partial exploded view.

The smart scale system 1000 is a cover layer 1080 (eg, bath mat cover, top layer), a generally opaque layer 1081, a pressure sensor (including a first sheet 1083, a second sheet 1084, and a third sheet 1085). Includes an array, substrate 1086, multiple load cells (including load cell 1021), multiple load feet (including load foot 1092), and base cover 1089. As shown, the plurality of load cells are coupled to the first side of the substrate 1086. The array of pressure sensors is coupled to the second opposite side of the substrate 1086. In some mounting embodiments, the substrate 1086 is one or more pieces of glass, such as two, four, or eight. In some implementations, the substrate 1086 contains two pieces of glass that are joined together via one or more hinges, which allows the Smart Scale System 1000 to fold in half for convenient portability. can.

In some implementations, the cover layer comprises a sheet of cloth. As shown in the figure, the cover layer 1080 includes two conductive cloth portions 1078A and 1078B separated from each other. In some implementations, the two conductive fabric portions 1078A, 1078B are at suitable distances, such as 1 inch, 2 inch, 3 inch, 4 inch, 5 inch, 6 inch, and up to the width of the cover layer 1080. They are separated from each other. In some implementations, the two conductive fabric portions 1078A and 1078B are at least 3 inches apart from each other. In some implementations, the two conductive fabric portions 1078A and 1078B are spaced apart from each other at a distance that the user's feet are normally separated from each other.

In some implementations, a plurality of electrodes 1044A and 1044B are positioned between the opaque layer 1081 and the cover layer 1080. Two electrodes 1044A and 1044B are shown in FIGS. 13A and 13B. Each of the electrodes 1044A and 1044B is positioned beneath one of the conductive cloth portions 1078A and 1078B. Therefore, even if the electrodes 1044A and 1044B are not exposed to the user, the electrodes 1044A and 1044B still have conductivity via the conductive cloth portions 1078A and 1078B. In other words, in some implementations, the conductive fabric portion is configured to be electrically and physically connected to the electrodes. In some implementations, under the cover layer 1080, the opaque layer 1081 is positioned above the various components, whereby the various components underneath are invisible to the human eye.

The array of pressure sensors is configured to generate pressure data associated with the user. In some implementations, the array of pressure sensors is configured to generate pressure data in response to the user's involvement in the system (eg, standing on the cover layer 1080). In some embodiments, the array of pressure sensors includes a first sheet 1083, a second sheet 1084, and a third sheet 1085. In some implementations, the first sheet 1083 is a copper row layer and comprises a plurality of conductive rows 1087. In some implementations, the third sheet 1085 is a copper row layer and comprises a plurality of conductive rows 1088. In some implementations, the second sheet 1084 is a pressure sensitive sheet and includes a piezo resistance sheet positioned between the first sheet 1083 and the third sheet 1085. The piezo resistance sheet is configured to change its electrical resistance according to the pressure applied to it. In some such embodiments, the intersection of each of the plurality of conductive rows 1087 and each of the plurality of conductive 1088 columns is a pressure sensor in an array of pressure sensors (eg, pressure sensor 912 in FIG. 12A). Form and / or define.

Multiple load cells are to generate weight data associated with the user. In some implementations, the plurality of load cells are configured to generate weight data depending on the user's involvement in the smart scale system (eg, standing on the cover layer 1080). In some embodiments, each of the plurality of load feet is rigid and is directly coupled to each one of the plurality of load cells. For example, as shown in FIGS. 13A and 13B, the rigid load foot 1092 is directly coupled to the load cell 1021. The base cover 1089 is coupled to the substrate 1086 so that the plurality of load cells 1021, the memory, and the control system are at least partially positioned between the base cover 1089 and the substrate 1086. In some embodiments, the base cover 1089 comprises a plurality of openings. Each of the plurality of rigid road feet projects at least partially through at least one of the plurality of openings. For example, the road foot 1092 partially protrudes from the opening 1091 of the base cover 1089. Therefore, while the load cell 1021 is not exposed to the ground, the load cell 1021 is stabilized through contact with the load foot 1092 and is effectively stabilized on the ground.

In some embodiments, one or more components of the Smart Scale System 1000 are smart mats, such as bath mats, yoga mats, entrance mats, anti-fatigue mats, chair cushions, pillows, shoe insoles, parts of carpets, 1 Form one or more tiles, one or more hardwood floorings, parts of mattresses, parts of showers (eg, combined or embedded in shower pans or bathtubs), or the like. This is advantageous because some people and / or animals may feel anxious about their weight. Hiding the smart scale system in everyday items can also encourage continuous monitoring of changes in weight, body fat distribution, and / or user health. In addition, energy harvesting can be included in some of the implementations referred to above, for example using dynamic pressure with foot heat and / or piezoelectric collectors.

In some embodiments, the smart mat includes all the components shown in FIGS. 13A and 13B. The smart mat can be of any suitable size. For example, the length of the smart mat is between about 20 cm and about 250 cm, preferably between about 40 cm and about 120 cm, and most preferably about 80 cm. The width of the smart mat is between about 15 cm and about 120 cm, preferably between about 30 cm and about 80 cm, and most preferably about 50 cm. The thickness of the smart mat is between about 5 mm and about 5 cm, preferably between about 8 mm and about 2 cm, and most preferably about 1.5 cm. Additional or alternative, in some implementations, the load foot 1092 extends from the base cover 1089 to about 2 mm to about 3 mm.

Referring to FIG. 14, a partial perspective view of the smart scale system 1100 is shown. The smart scale system 1100 is the same as or similar to the smart scale system 1000, and similar reference numbers refer to similar elements and / or components. However, the array of pressure sensors in the smart scale system 1100 is not three sheets (eg, first sheet 1083, second sheet 1084, and third sheet in FIGS. 13A and 13B), but two sheets (eg, third sheet). , The first sheet 1184 and the second sheet 1182) of FIG. 14 are included.

As shown, the first sheet 1184 of the smart scale system 1100 is the same as or similar to the second sheet 1084 of the smart scale system 1000. In some implementations, the first sheet 1184 is a pressure sensitive sheet such as a piezo resistance sheet. In some implementations, the first sheet 1184 is flexible. The second sheet 1182 of the smart scale system 1100 is replaced at the same time as the first sheet 1083 and the third sheet 1085 of the smart scale system 1000. In some implementations, the second sheet 1182 comprises a printed circuit board (PCB) having a plurality of conductive trace patterns (eg, 1112A-1112E) on it. In some such implementations, each of the plurality of conductive trace patterns forms and / or defines a pressure sensor in an array of pressure sensors (eg, the pressure sensor of FIG. 12A).

Next, with reference to FIG. 15A, an exemplary pressure sensor formed and / or defined by a conductive trace pattern 1112 according to some of the embodiments of the present disclosure is shown. As shown, the conductive trace pattern 1112 includes an inner disk 1105 and an outer ring 1103. The inner disk 1105 is radially separated from the outer ring 1103 by a first distance d. Examples of the first distance d include 100 μm, 150 μm, 200 μm, 250 μm, 300 μm, 400 μm, 500 μm, 600 μm, 700 μm, 800 μm, 900 μm, and 1000 μm. In some implementations, the first distance d is 0.8 mm, which is 800 μm.

The outer ring 1103 is formed around the inner disk 1105 at a second distance. Examples of the second distance θ include 90 °, 135 °, 180 °, 225 °, 270 °, 315 °, and 360 °. As shown in FIG. 14, the conductive trace pattern 1112A has an outer ring forming a perfect circle around the inner disk with a second distance θ of 360 °. Alternatively, in some implementations, the outer ring 1103 is not formed all around the inner disk 1105, so that the second distance θ is less than 360 ° (best shown in FIG. 15A).

Next, referring to FIG. 15B, in some implementations, the outer ring of the conductive trace pattern is an equilateral polygon. For example, the conductive trace pattern 1112A is positioned adjacent to the conductive trace pattern 1112B. The conductive trace pattern 1112A includes an inner disk 1105A and an outer ring 1103A, and the outer ring 1103A is a regular hexagon. The regular hexagon of the outer ring 1103A has six sides, and one side of the outer ring 1103A of the conductive trace pattern 1112A is adjacent to and parallel to one side of the outer ring of the conductive trace pattern 1112B. The length of each side is between about 1 mm and about 15 mm, such as 1 mm, 2 mm, 3 mm, 4 mm, 5 mm, 6 mm, 7 mm, 8 mm, 9 mm, 10 mm, 11 mm, 12 mm, 13 mm, 14 mm, or 15 mm.

Now move on to FIGS. 16A-16D. FIG. 16A shows a smart scale system (for example, smart scale system 100, smart scale system 200, smart scale system 300, smart scale system 400, smart scale system 700, smart scale system 800, smart scale system 900, smart scale system 1000, And the first layout 1200A of the load cell in the smart scale system 1100). In this layout 1200A, the plurality of load cells includes four single load cells 1221. In some embodiments, in this layout 1200A, the plurality of load cells comprises one 4x4 array of the above load cells.

FIG. 16B shows a smart scale system (for example, smart scale system 100, smart scale system 200, smart scale system 300, smart scale system 400, smart scale system 700, smart scale system 800, smart scale system 900, smart scale system 1000, And the second layout 1200B of the load cell in the smart scale system 1100). In this layout 1200B, the plurality of load cells include 6 of the load cells 1221 as shown in FIG. 16A. In some embodiments, in this layout 1200B, the plurality of load cells comprises one 2x3 array of load cells.

FIG. 16C shows a smart scale system (for example, smart scale system 100, smart scale system 200, smart scale system 300, smart scale system 400, smart scale system 700, smart scale system 800, smart scale system 900, smart scale system 1000, And the third layout 1200C of the load cell in the smart scale system 1100). In this layout 1200C, the plurality of load cells include 9 of the load cells 1221. In some embodiments, in this layout 1200C, the plurality of load cells comprises one 3x3 array of load cells.

FIG. 16D shows a smart scale system (for example, smart scale system 100, smart scale system 200, smart scale system 300, smart scale system 400, smart scale system 700, smart scale system 800, smart scale system 900, smart scale system 1000, And the fourth layout 1200D of the load cell in the smart scale system 1100). In this layout 1200D, the plurality of load cells includes eight single load cells 1221. In some implementations, in this layout 1200D, the plurality of load cells includes two of the 4x4 arrays of the above load cells. In some implementations, the fourth layout 1200D includes two smart scale systems with a first layout 1200A coupled to each other via one or more hinges 1230.

According to some embodiments of the present disclosure, an array of pressure sensors has a thickness (eg, a three-dimensional sensor) and / or a material used on its surface (eg, a coplanar sensor) for pressure sensing. Can include sheets. In some embodiments, the material is an insulating polymer charged with conductive particles. Low currents can experience tunneling effects from conductive particles to other particles. In some implementations, this material is deformable. In addition, the distance between the conductive particles varies with the applied vertical pressure (see FIGS. 20A and 20B).

FIG. 20A shows a first scheme 2000A in a pressure sensing sheet 2010 prior to vertical application pressure, according to some of the embodiments of the present disclosure. The current 2050A travels through the conductive particles 2020. FIG. 20B shows a second scheme 2000B in a pressure sensing sheet 2010 after vertical application pressure according to some of the embodiments of the present disclosure. The current 2050B travels through the conductive particles 2020 and the adjacent conductive particles 2030.

式中、ｐは接触面の抵抗率、Ｆは表面に対する法線力、Ｋは、とりわけ、材料の弾性に依存する関数である。 When pressure is applied to the material, the conductive particles approach each other (FIG. 20B), increasing the contribution of the tunneling effect to the current circulation. The relationship between impedance and applied force can be written as follows.

In the equation, p is the resistivity of the contact surface, F is the normal force to the surface, and K is a function that depends, among other things, on the elasticity of the material.

However, K is not a constant, and the relationship between pressure and resistivity is not linear. Otherwise, grinding the material is only possible if the material itself is free to stretch in the other two dimensions, which is not the case herein and the deformation is only local. do not have.

Therefore, in some implementations, the value to be measured is resistance. The resistance here is not linear with respect to pressure. Moreover, pressure changes cannot be easily measured in the required pressure slots.

In some implementations, 3D sensors are not optimal because the change in resistance due to pressure is not sufficient under high pressure. Therefore, the industrialization of pressure sensor arrays is more complex and it is difficult to have a sensor shape that meets the needs of multiple sensors in a small area (eg, 4 sensors per square centimeter). In fact, in such a situation, the individual sensors can only take up a space of up to 2.5 x 2.5 mm ² , and the resistance of the individual sensors is significantly reduced.

In the case of a coplanar sensor, the measurable magnitude is its resistance. To limit the consumption of the pressure sensor array and / or the crosstalk between adjacent pressure sensors, the resistance value should be as high as possible. In some implementations, changes in resistance are significant throughout the range of use of the array of pressure sensors, so that the slope of the characteristic is steep enough on an overall scale to be correctly defined. Therefore, the preferred shape allows for efficient pavement of the plane.

Since the value to be measured is resistance, one solution is to use a transimpedance amplifier (TIA). FIG. 21 shows a schematic 2100 of a transimpedance amplifier according to some of the embodiments of the present disclosure. The circuit is powered using an asymmetric power supply. The transimpedance amplifier has a virtual stable ground with the lowest possible internal impedance.

The relationship between the input current i and the output voltage VMES ₁ is given by the following equation in the first approximate value.

が差動電圧である場合、例えば以下のようになる。

However, the array of pressure sensors is not determined by this first approximation.

When is a differential voltage, for example, it becomes as follows.

In this new notation, the relationship between the measured current and the output voltage is as follows.

However, the value to be measured is the sensor resistance, which makes it possible to calculate the current i due to the forced characteristics of the operational amplifier. In linear mode, the voltage is V ₋ . With the resistance of the sensor R _c , the scheme becomes as shown in FIG. 22 showing the schematic 2200 in a transimpedance amplifier according to some implementations of the present disclosure.

The current of FIG. 22 circulates in the same direction as the current of FIG. Next, the output voltage is given by the following equation.

In some implementations, the power supply should use a 5V power supply _Vcc and a rail-to-rail amplifier at the output. Nevertheless, this supply voltage limitation imposes restrictions on the choice of resistance R _f . Therefore, the limiting condition is given by the following equation.

In some implementations, f is very low and can be close to zero. Therefore, when f is equalized to 0, it becomes as follows.

The resistance R _c of the sensor changes greatly. In order to avoid saturation of the amplifier, a resistance R _f below the minimum impedance of the array of pressure sensors is mounted. To limit the consumption of the amplifier, the resistance R _f is chosen relative to the specification to be the resistance of the array of pressure sensors when placed under maximum pressure.

Furthermore, the coplanar sensor alone can only measure the average pressure on the surface between the two electrodes. It is not possible to measure an accurate image of the applied pressure. In order to obtain more accurate images, juxtaposition of sensors is used, which is problematic for the placement of those sensors on a plane.

To solve the above problems, the present disclosure provides optimal geography of flat pavement, as illustrated in the second sheet 1182 of the smart scale system 1100 of FIG. The distance between adjacent sensors (eg, between the conductive trace pattern 1112A and the conductive trace pattern 1112B) does not cover the entire circumference of the outer ring (eg, the outer ring 1103 shown in FIG. 15A). If (eg, the second distance θ is less than 360 °), it must be sufficient to avoid crosstalk. In fact, the resistance of the sensor is proportional to the outer circumference of the outer ring and the distance between the two electrodes. In some implementations, the outer circumference of the outer ring is limited in order to increase the resistance of the sensor (eg, the outer ring is not a perfect ring and θ is less than 360 °). In other words, if there is less contact (eg, the ring is incomplete), the resistance will be higher.

Referring to FIG. 17A, the smart scale system 1300 is such that the smart scale system 1300 is a cat, dog, horse, hamster, guinea pig, rabbit, chinchilla, mouse, rat, parrot, yadkari, ferret, reptile, fish, sea monkey, or. It is the same as or similar to the Smart Scale System 1000 or the Smart Scale System 1100, except that it has been modified for pets such as any combination thereof. In some implementations, the smart scale system is customized for non-static items that move, walk, crawl, and roll across the weighing surface. For example, the smart scale system 1300 calculates the average of the measured weights, ignoring the landing and takeoff areas.

As shown in FIG. 17A, dog 1360 is using the smart scale system 1300. For example, the dog 1360 steps on the smart scale system 1300 and the measured weight is 0-30 kg and then about 23 kg in a few seconds. After that, the dog 1360 leaves and the measured weight is reduced. The smart scale system 1300 then averages all the values measured in a few seconds and thus determines that the dog 1360 weighs 23 kg. In other words, in some implementations, the weight of a non-static item can be estimated from the moment it fluctuates around a particular value that indicates the actual weight of the non-static item.

The layout and properties of the load cell differ depending on the type of pet. For example, a smart scale system customized for dogs includes a weight range of about 0.3 kilograms to about 100 kilograms. As disclosed herein, an array of pressure sensors in a smart scale system can be configured to sense pressure data. FIG. 17B shows a pressure map 1366 of two paws 1362 and 1364 of a dog (or other type of pet) in a smart scale system, according to some embodiments of the present disclosure. In some implementations, pressure data for all four dog paws are measured and included in the pressure map 1366. The pressure map 1366 represents the pressure gradient associated with the two legs 1362 and 1364. In addition, pressure map 1366 can show the weight distribution of dogs.

Used in combination with or without the pressure map 1366, the pressure data is the same as or similar to that shown in FIG. 7 and described accordingly. It can be used to generate additional information associated with dogs (or other types of pets). In addition, the pressure map 1366 may include the pressure points of the foot. Therefore, the pressure map 1366 shows various discomforts and / or illnesses of dogs (or other types of pets) in the same or similar manner as shown in FIG. 7 and described accordingly. May be useful for detection instantly and / or over time.

In some implementations, the array of pressure sensors in a smart scale system is configured to sense temperature data in a manner similar to or similar to that shown in FIG. 8 and described accordingly. can do. For example, FIG. 17C shows temperature maps 1368 of two paws 1362 and 1364 of a dog (or other type of pet) in a smart scale system, according to some embodiments of the present disclosure. In some implementations, temperature data for all four dog paws are measured and included in temperature map 1368. The heat from the dog can be used to power the battery of the power supply of the smart mat system, such as that shown in FIG. 2 of the present disclosure.

In some implementations, weight and / or pressure data is used (eg, based on weight range, based on footprints, based on thermal maps, based on temperature maps or any combination thereof. ) The type and / or category of non-static items can be determined. Alternatively or additionally, weight and / or pressure data can be used to identify the user regardless of whether the user is human or animal.

Next, with reference to FIG. 18, an exemplary block diagram 1600 of the smart scale system 1610 according to some implementations of the present disclosure is shown. The smart scale system 1610 includes one or more sensors 1612, which can include one or more load cells as disclosed herein. In some implementations, the smart scale system 1610 has been modified to detect animals smaller than typical humans, especially cats and dogs. In some embodiments, the smart scale system 1610 may further include an interface 1638 that may include display LEDs and / or buttons. The smart scale system 1610 also includes an electronic system having a power supply 1634, a signal conditioning processing module 1615, a central module 1617, a communication module 1614, or any combination thereof. The communication module 1617 is wirelessly coupled (eg, via Bluetooth) to a mobile device such as a mobile phone 1650. Alternatively or additionally, the communication module 1617 is coupled to a smart plug, which is wirelessly coupled to a mobile device.

FIG. 19A shows a smart scale system 1700 adapted for use in a bed according to some of the embodiments of the present disclosure. In some embodiments, the smart scale system 1700 is adapted for use in a crib, which also functions as a baby monitoring system. The smart scale system 1700 is the same as or similar to the smart scale system 1000, the smart scale system 1100, or the smart scale system 1300. However, although the load cell 1721 of the smart scale system 1700 is located within the legs of the bed and is sometimes hidden, the array of pressure sensors 1712 is coupled and / or embedded in the mattress. In some embodiments, the smart scale system 1700 (i) analyzes the user's sleep quality, (ii) detects sleep disorders (eg, sleep apnea), and (iii) sleep. It is further configured to detect location, (iv) determine changes in sleep behavior, or (v) make any combination thereof.

FIG. 19B shows a smart scale system 1800 adapted for use in a shower according to some embodiments of the present disclosure. The smart scale system 1700 is the same as or similar to the smart scale system 1000, the smart scale system 1100, or the smart scale system 1300. However, the smart scale system 1800 is coupled to the shower pan 1880. In some embodiments, the shower pan 1880 is made of flexible glass, fiberglass, plastic, ceramic, or any combination thereof. Therefore, the smart scale system 1800 is configured to weigh the user 1850 while taking a shower. In some embodiments, the shower pan 1880 is positioned on top of the smart scale system 1800, whereby the shower pan 1880 prevents at least a portion of the smart scale system 1800 from getting wet.

In some embodiments, the smart scale system 1800 includes a load cell 1821 under a shower pan 1880, and an energy harvesting device that uses a hydraulic and / or water supply turbine. The load cell 1821 is configured to measure the vertical displacement of the shower pan. The seal on the side of the shower pan 1880 will stop the shower pan from lowering slightly, thus reducing the weight of the user 1850 slightly. Therefore, the smart scale system 1800 is configured to adjust its estimates and / or calculations to take into account its weight loss and return it to its measured weight.

In some embodiments, the smart scale system 1800 uses (i) supplied hot and / or cold water flowing through the pipe to the shower head, and (ii) drainage (eg, a filter for removing hair). The drainage pipe is narrowed to increase the pressure and flow rate, thereby increasing the amount of power generated from the drainage), or (iii) both are used to supply power. Additional or alternative, the smart scale system 1800 includes a weighing system disguised as a tile, which can be embedded in a shower pan 1880 and ultimately utilizes the drainage and / or supply of water. Powered by a turbine.

Disclosure Computers and Hardware Implementations It is first understood that the disclosures herein can be implemented in any type of hardware and / or software and can be pre-programmed general purpose computing devices. It should be. For example, the system can be implemented using a server, personal computer, portable computer, thin client, or any suitable single or multiple device. The present disclosure and / or its components together using any suitable communication protocol by any communication medium such as a single device in a single location, or an electrical cable, fiber optic cable, or wireless mode. It can be multiple devices in a single or multiple locations connected.

It should also be noted that the present disclosure is exemplified and considered herein as having multiple modules performing a particular function. It should be understood that these modules are only outlined based on their functionality for the purpose of clarity and do not necessarily represent specific hardware or software. In this regard, these modules can be hardware and / or software implemented to substantially perform the particular function considered. In addition, the modules can be combined together within the present disclosure or can be subdivided into additional modules based on the particular function desired. Therefore, the present disclosure should not be construed as limiting the present disclosure, but should be understood solely to illustrate the implementation of the example.

Computing systems can include clients and servers. Clients and servers are generally remote to each other and usually interact through a communication network. The client-server relationship is created by a computer program that runs on each computer and has a client-server relationship. In some implementations, the server sends data (eg, an HTML page) to a client device (eg, for the purpose of displaying data and receiving user input from a user interacting with the client device). Data generated on the client device (eg, the result of a user dialogue) can be received from the client device on the server.

Implementations of the subject matter described herein include, for example, a backend component as a data server, or a middleware component such as an application server, or, for example, the user described herein. Computing that includes a front-end component with a graphical user interface or web browser that can interact with the implementation of the subject, or any combination of one or more such back-ends, middleware, or front-end components. Can be implemented in the system. The components of the system can be interconnected by any form or medium of digital data communication, such as a communication network. Examples of communication networks include local area networks (“LAN”) and wide area networks (“WAN”), internetworks (eg, the Internet), and peer-to-peer networks (eg, ad hoc peer-to-peer networks).

Implementations of the subject matter and operations described herein are in digital electronic circuits, or in computer software, firmware, or hardware, including the structures and structural equivalents thereof disclosed herein. Alternatively, it can be carried out in one or more combinations thereof. An implementation of the subject matter described herein is one or more computer programs encoded on a computer storage medium to be performed by a data processing apparatus or to control its operation. That is, it can be implemented as one or more modules of computer program instructions. Alternatively or further, the program instruction is an artificially generated propagating signal, eg, a machine-generated electrical signal generated to encode information to be transmitted to a receiver suitable for execution by a data processing device. Can be encoded into an optical or electromagnetic signal. The computer storage medium can be or include a computer readable storage device, a computer readable storage board, a random or serial access memory array or device, or a combination thereof. Further, although the computer storage medium is not a propagating signal, the computer storage medium can be the source or destination of the computer program instructions encoded in the artificially generated propagating signal. The computer storage medium can also be or be included in one or more separate physical components or media (eg, multiple CDs, disks, or other storage devices).

The actions described herein are performed as actions performed by a "data processor" on data stored in one or more computer-readable storage devices or received from other sources. can do.

The term "data processing device" includes all types of devices, devices, and machines for processing data, such as programmable processors, computers, systems on chips, or a combination of the above. including. The device can include logic circuits for special purposes such as FPGAs (Field Programmable Gate Arrays) or ASICs (Application Specific Integrated Circuits). In addition to hardware, the device is code that creates the execution environment for computer programs, such as processor firmware, protocol stacks, database management systems, operating systems, cross-platform runtime environments, virtual machines, or one or more of them. Codes that make up the combination of can also be included. Equipment and execution environments can implement a variety of different computing model infrastructures, including web services, distributed computing, and grid computing infrastructure.

Computer programs (also called programs, software, software applications, scripts, or code) can be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, either as standalone programs or as stand-alone programs. It can be deployed in any format, including as modules, components, subroutines, objects, and other units suitable for use in computing environments. Computer programs may, but do not need to, support files in the file system. A program may be in a portion of a file that holds other programs or data (eg, one or more scripts stored in a markup language document), in a single file dedicated to that program, or in multiple adjustments. It can be stored in a file (eg, a file that stores one or more modules, subprograms, parts of code). Computer programs can be deployed to run on one computer, or on multiple computers located at one site or distributed across multiple sites and interconnected by communication networks.

The processes and logical flows described herein are performed by one or more programmable processors running one or more computer programs, and actions can be performed by manipulating input data to produce output. .. Processes and logic flows can also be run by special purpose logic circuits such as FPGAs (Field Programmable Gate Arrays) or ASICs (Application Specific Integrated Circuits), and the device can also be implemented as special purpose logic circuits. can.

Suitable processors for running computer programs include, for example, both general purpose and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, the processor receives instructions and data from read-only memory and / or random access memory. An essential element of a computer is a processor for performing actions according to instructions and one or more memory devices for storing instructions and data. In general, a computer also includes one or more mass storage devices for storing data, such as magnetic, magnetic optical discs, or optical discs, or receives data, or transfers data thereof. It is operably combined to do both. However, the computer does not need such a device. In addition, the computer may be another device, such as a mobile phone, personal digital assistant (PDA), mobile audio or video player, game console, Global Positioning System (GPS) receiver, or portable, to name just a few. It can be incorporated into a storage device (eg, a universal serial bus (USB) flash drive). Suitable devices for storing computer program instructions and data include, for example, semiconductor memory devices such as EPROMs, EEPROMs, flash memory devices, magnetic disks such as internal hard disks or removable disks, magneto-optical disks, CD ROMs and Includes all forms of non-volatile memory, media, and memory devices, including DVD-ROM disks. Processors and memory can be complemented or incorporated by logic circuits of special purpose.

Additional Implementations According to some implementations of the present disclosure, a system for determining a user's user profile includes mats, cameras, display devices, processors, and memory devices. The mat includes a first sensor configured to output pressure data. The camera is configured to generate reproducible image data as one or more images of the user. The memory device is configured to receive and store pressure data from the first sensor and image data from the camera. The memory device stores machine-readable instructions that are configured to cause the processor to determine that a portion of the user is in contact with the mat based on pressure data, image data, or both. The processor also causes the user's user profile to be determined based on pressure data, image data, or both. The user profile includes the posture of the user. The user's posture is determined by comparing the pressure data, the image data, or both with one or more predetermined postures stored in the memory device. The processor also displays the information associated with the determined user profile on the display device.

According to some implementations of the present disclosure, a system for determining a user profile of a user includes a mat, a camera, a display device, a processor, and a memory device. The mat includes a first sensor configured to output pressure data. The camera is configured to generate reproducible image data as one or more images of the user. The memory device is configured to receive and store pressure data from the first sensor and image data from the camera. The memory device stores machine-readable instructions that are configured to cause the processor to determine that a portion of the user is in contact with the mat based on pressure data, image data, or both. The processor further determines the user profile of the user based on the pressure data and the image data. The user profile includes the posture of the user. The posture of the user is determined by comparing the pressure data and the image data with one or more predetermined postures stored in the memory device. The processor also displays the information associated with the determined user profile on the display device.

According to some implementations of the present disclosure, a system for determining a user profile of a user includes a mat, a display device, a processor, and a memory. The mat includes a battery, a first sensor configured to output pressure data, and a second sensor configured to output temperature data. The second sensor includes a transducer configured to convert thermal energy into electrical energy to charge the battery. The memory device is configured to receive and store pressure data from the first sensor and temperature data from the second sensor. The memory device stores machine-readable instructions that are configured to cause the processor to determine that a portion of the user is in contact with the mat based on pressure data, temperature data, or both. The processor is further configured to determine the user profile of the user based on pressure and temperature data. The user profile includes the posture of the user. The posture of the user is determined by comparing the pressure data and the temperature data with one or more predetermined postures stored in the memory device. The processor also displays the information associated with the determined user profile on the display device.

According to some embodiments of the present disclosure, a method for determining a user's posture comprises receiving pressure data and image data from a smart scale system. Smart scale systems include mats, cameras and display devices. The mat has a first sensor configured to output pressure data. The camera is configured to generate reproducible image data as one or more images of the user. This method further stores the received pressure data and the received image data on a memory device, and a portion of the user contacts the mat based on the received pressure data, the received image data, or both. Determining that it is doing, comparing received pressure data, received image data, or both with one or more predetermined postures stored in a memory device, and at least partially comparing. To determine the user profile of a user based on, that the user profile includes the attitude of the user, that the determination, and that the information associated with the determined user profile be displayed on the display device. including.

According to some embodiments of the present disclosure, a smart scale system comprises a substrate, multiple load cells coupled to the first side of the substrate, an array of pressure sensors coupled to the second opposite side of the substrate. Includes memory and control system. Multiple load cells are configured to generate weight data associated with the user. The array of pressure sensors is configured to generate pressure data associated with the user. Registered user data and machine-readable instructions are stored in the memory. The control system is coupled to memory and is arranged to provide control signals to one or more processors configured to execute machine-readable instructions. Weight data is received from multiple load cells. Pressure data is received from the array of pressure sensors. Based on pressure data and registered user data, at least in part, the user is determined to be a non-registered user of the smart scale system. The display device prompts you to register the user as a registered user of the smart scale system.

According to some embodiments of the present disclosure, a smart scale system comprises a substrate, multiple load cells coupled to the first side of the substrate, an array of pressure sensors coupled to the second opposite side of the substrate. Includes memory and control system. Multiple load cells are configured to generate weight data associated with the user. The array of pressure sensors is configured to generate pressure data associated with the user. Registered user data and machine-readable instructions are stored in the memory. The control system is coupled to memory and is arranged to provide control signals to one or more processors configured to execute machine-readable instructions. Weight data is received from multiple load cells. Pressure data is received from the array of pressure sensors. Based on pressure data and registered user data, at least in part, the user is determined to be a registered user of the smart scale system. The display device prompts the user to enter information associated with the weight data received.

Some implementations of the present disclosure disclose methods for determining a user's normalized weight. The registered user data is received from the memory of the smart scale system. The registered user data includes past weight data, past user information, and past normalized weight data. Machine learning algorithms are trained using historical weight data, historical user information, and historical normalized weight data. The pressure data associated with the user is received from the array of pressure sensors in the smart scale system. The current weight data associated with the user is received from multiple load cells in the smart scale system. Based on pressure data and registered user data, at least in part, the user is determined to be a registered user of the smart scale system. The display device prompts the user to enter information associated with the current weight data. In response to the prompt, the current user information is received. The current weight data and current user information associated with the user are received as inputs to the machine learning algorithm. The user's normalized weight is generated as the output of the machine learning algorithm.

Selected Embodiments and Implementation Embodiments The above description and the appended claims disclose some embodiments and / or implementation embodiments of the present disclosure, while other alternative embodiments of the present disclosure are present. It is disclosed in the following further embodiments.

Embodiment 1. A system for determining a user's user profile.
A mat containing a first sensor configured to output pressure data,
A camera configured to generate reproducible image data as one or more images of the user, and
With display devices
With the processor
A memory device comprising: a memory device configured to receive and store pressure data from a first sensor and image data from a camera, the memory device in the processor.
Determining that a portion of the user is in contact with the mat based on pressure data, image data, or both.
Determining a user profile of a user based on pressure data, image data, or both, wherein the user profile includes the user's posture and the user's posture stores pressure data, image data, or both. Determining a user profile, which is determined by comparing it to one or more predetermined postures stored in the device.
A system that stores machine-readable instructions that are configured to display and perform on a display device the information associated with the determined user profile.

Embodiment 2. The system of embodiment 1, wherein the memory device is further configured to allow a processor to determine a user's identity based on pressure data, image data, or both.

Embodiment 3. The system of embodiment 2, wherein determining the user's identity involves using a machine learning algorithm.

Embodiment 4. The system according to any one of embodiments 1 to 3, wherein the user profile includes the shape of a part of the user, the dimensions of the part of the user, or both.

Embodiment 5. The display information associated with the determined user profile is a first sign indicating the weight of the user, a second sign indicating the posture of the user, a third sign indicating the shape of a part of the user, and the dimensions of the part of the user. 4. The system of embodiment 4, comprising a fourth sign indicating, or any combination thereof.

Embodiment 6. The system of any one of embodiments 1-5, wherein the mat comprises a second sensor configured to output temperature data.

Embodiment 7. The system of embodiment 6 wherein the memory device is further configured to cause the processor to determine that a portion of the user is in contact with the mat based on temperature data.

Embodiment 8. The system of any one of embodiments 1-7, wherein the camera is coupled to a mobile device.

Embodiment 9. The system of any one of embodiments 1-8, wherein the mat further comprises a battery and an energy harvester, wherein the energy harvester is configured to collect energy for charging the battery.

Embodiment 10. The system of embodiment 9, wherein the energy harvester is a transducer configured to convert thermal energy into electrical energy to charge the battery.

Embodiment 11. The system of embodiment 10, wherein the transducer is coupled to a second sensor configured to output temperature data.

Embodiment 12. The system of any one of embodiments 1-11, comprising a user interface in which the display device is configured to receive input data associated with the user.

Embodiment 13. The system of embodiment 12, wherein the input data includes the age of the user, the gender of the user, or both.

Embodiment 14. The memory device is further configured to cause the processor to determine the wellness plan of the user based on the determined user profile, and the display information associated with the determined user profile indicates the wellness of the user. The system according to any one of embodiments 1 to 13.

Embodiment 15. The system of embodiment 14, wherein the wellness plan is an exercise schedule.

Embodiment 16. A memory device is further configured to cause the processor to determine a posture score based on comparing pressure data, image data, or both with one or more predetermined postures, wherein the posture score is a user. A system according to any one of embodiments 1 to 15, which indicates that the posture of the device is bad.

Embodiment 17. The memory device is further configured to cause the processor to determine a posture correction plan associated with the user based on comparing pressure data, image data, or both with one or more predetermined postures. Any one of embodiments 1-16.

Embodiment 18. The system of any one of embodiments 1-17, wherein the processor and memory device are coupled to a mat.

Embodiment 19. The system of any one of embodiments 1-18, wherein the display device, processor, and memory device are coupled to the remote device.

20. The system of any one of embodiments 1-19, wherein the display device is coupled to a mirror, carpet, mat, or mobile device.

21. Embodiment 21. The system according to any one of embodiments 1 to 20, wherein a part of the user is a part of the foot of the user.

Embodiment 22. The system of any one of embodiments 1-21, wherein the mat is flexible.

23. The system of embodiment 22, wherein the mat is configured to move between a generally planar configuration and a generally cylindrical configuration.

Embodiment 24. The system according to any one of embodiments 1 to 23, wherein the first sensor is a CMOS integrated silicon pressure sensor.

Embodiment 25. The system according to any one of embodiments 1 to 24, wherein the first sensor is a piezoelectric sensor.

Embodiment 26. The system of any one of embodiments 1-25, wherein the first sensor comprises a liquid embedding layer and the embedding layer is configured to detect pressure on the mat.

Embodiment 27. The system of embodiment 26, wherein the first sensor is a laminated pressure sensor comprising a liquid metal embedded elastomer.

Embodiment 28. The system of any one of embodiments 1-27, wherein the memory device is further configured to cause the processor to determine the active period based on the determination that a portion of the user is in contact with the mat.

Embodiment 29. A system of embodiment 28 further comprising a virtual reality device configured to receive pressure data from a first sensor and image data from a camera during an active period and display digital information based on the received data. ..

30. The system of embodiment 29, wherein the display device is coupled to a virtual reality device.

Embodiment 31. The system of any one of embodiments 1-30, wherein the display device is communicably coupled to the processor via Bluetooth.

Embodiment 32. The system according to any one of embodiments 1 to 31, wherein the mat is disposable.

Embodiment 33. A system for determining a user's user profile.
A mat containing a first sensor configured to output pressure data,
A camera configured to generate reproducible image data as one or more images of the user, and
With display devices
With the processor
A memory device comprising: a memory device configured to receive and store pressure data from a first sensor and image data from a camera, the memory device in the processor.
Determining that a portion of the user is in contact with the mat based on pressure data, image data, or both.
Determining a user profile of a user based on pressure data and image data, wherein the user profile includes the posture of the user, and the posture of the user is one or more in which the pressure data and the image data are stored in the memory device. Judging the user profile, which is determined by comparing with the predetermined posture of
A system that stores machine-readable instructions that are configured to display and perform on a display device the information associated with the determined user profile.

Embodiment 34. A system for determining a user's user profile.
A mat containing a battery, a first sensor configured to output pressure data, and a second sensor configured to output temperature data, for the second sensor to charge the battery. Includes a transducer configured to convert thermal energy to electrical energy, with a matte,
With display devices
With the processor
A memory device comprising: a memory device configured to receive and store pressure data from a first sensor and temperature data from a second sensorer, the memory device in the processor.
Determining that some of the users are in contact with the mat based on pressure data, temperature data, or both.
Determining a user profile of a user based on pressure and temperature data, wherein the user profile includes the user's attitude and the user's attitude is one or more of the pressure and temperature data stored in a memory device. Judging the user profile, which is determined by comparing with the predetermined posture of
A system that stores machine-readable instructions that are configured to display and perform on a display device the information associated with the determined user profile.

Embodiment 35. It is a method for judging the posture of the user.
Receiving pressure data and image data from the smart scale system, the smart scale system,
A mat with a first sensor configured to output pressure data,
Receiving and including a camera and display device configured to generate reproducible image data as one or more images of the user.
Storing received pressure data and received image data in a memory device,
Determining that some of the users are in contact with the mat based on the received pressure data, the received image data, or both.
Comparing received pressure data, received image data, or both with one or more predetermined postures stored in a memory device, and
Determining a user's user profile, at least in part, based on comparison, and determining that the user profile includes the user's attitude.
A method, including displaying information associated with a determined user profile on a display device.

Embodiment 36. It ’s a smart scale system.
With the board
Multiple load cells coupled to the first side of the board, configured to generate weight data associated with the user, and
An array of pressure sensors coupled to a second opposite side of the substrate, the array of pressure sensors configured to generate pressure data associated with the user.
Memory for storing registered user data and machine-readable instructions,
A control system that is coupled to memory
Receiving weight data from multiple load cells and
Receiving pressure data from an array of pressure sensors,
Determining that a user is a registered user of a smart scale system, at least in part, based on pressure data and registered user data.
Providing control signals to one or more processors configured to perform machine-readable instructions to display a prompt on a display device to register a user as a registered user of a smart scale system. A smart scale system, with a control system arranged so that it is equipped with.

Embodiment 37. The smart scale system of embodiment 36 further comprising a cover layer.

Embodiment 38. The smart scale system of embodiment 37, wherein the cover layer comprises a sheet of cloth.

Embodiment 39. The smart scale system of embodiment 38, wherein the sheets of cloth include two pieces of conductive cloth that are spaced apart from each other.

Embodiment 40. The smart scale system of Embodiment 39, wherein the two conductive fabric portions are separated from each other by at least 3 inches.

Embodiment 41. The smart scale system according to any one of embodiments 36 to 40, wherein the substrate is one or more pieces of glass.

Embodiment 42. The smart scale system of embodiment 41, wherein the substrate comprises two pieces of glass coupled together via one or more hinges.

Embodiment 43. The smart scale system according to any one of embodiments 36 to 42, further comprising a plurality of rigid feet.

Embodiment 44. The smart scale system of embodiment 43, wherein each of the plurality of rigid feet is directly coupled to one of each of the plurality of load cells.

Embodiment 45. The smart scale of embodiment 44, further comprising a base cover, wherein the base cover is coupled to the board so that a plurality of load cells, memories, and control systems are at least partially positioned between the base cover and the board. system.

Embodiment 46. The smart scale system of embodiment 45, wherein the base cover comprises a plurality of openings, each of the plurality of rigid feet projecting at least partially through at least one of the plurality of openings.

Embodiment 47. The method of any one of embodiments 36-46, wherein the plurality of load cells are configured to generate weight data depending on the user involved in the smart scale system.

Embodiment 48. The smart scale system of embodiment 47, wherein the user involved in the smart scale system includes a user standing on the cover layer of the smart scale system.

Embodiment 49. The smart scale system of any one of embodiments 36-48, wherein the plurality of load cells include a 4x4 array of load cells and the 4x4 array of load cells is coupled to an analog-to-digital converter.

Embodiment 50. One of embodiments 36-49, wherein the plurality of load cells include four of the 4x4 arrays of load cells, and each of the 4x4 arrays of load cells is coupled to their respective analog-to-digital converters. One smart scale system.

Embodiment 51. The smart scale system of any one of embodiments 36-50, wherein the array of pressure sensors is configured to generate pressure data depending on the users involved in the system.

Embodiment 52. The smart scale system of embodiment 51, wherein the user involved in the smart scale system includes a user standing on the cover layer of the smart scale system.

Embodiment 53. The smart scale system of any one of embodiments 36-52, wherein the array of pressure sensors comprises a 100 × 70 matrix of pressure sensors.

Embodiment 54. The smart scale system according to any one of embodiments 36 to 53, wherein the array of pressure sensors includes a first sheet, a second sheet, and a third sheet.

Embodiment 55. The smart scale system of embodiment 54, wherein the second sheet comprises a piezo resistance sheet positioned between the first sheet and the third sheet.

Embodiment 56. The smart scale system of embodiment 55, wherein the first sheet comprises a plurality of conductive rows.

Embodiment 57. The smart scale system of embodiment 56, wherein the third sheet comprises a plurality of conductive rows.

Embodiment 58. The smart scale system of embodiment 57, wherein the intersection of each of the plurality of conductive rows and each of the plurality of conductive columns defines a pressure sensor in an array of pressure sensors.

Embodiment 59. The smart scale system of any one of embodiments 36-58, further comprising a generally opaque layer coupled to an array of pressure sensors.

Embodiment 60. Further comprising a bioelectrical impedance system configured to generate bioelectrical impedance data associated with the user so that the bioelectrical impedance system makes conductive contact with the user and forms a first closed circuit with the user. The smart scale system of embodiment 59, comprising a plurality of configured electrodes.

Embodiment 61. The smart scale system of embodiment 60, wherein at least one of the plurality of electrodes is positioned between the approximately opaque layer of the smart scale system and the cover layer, the cover layer comprising an electron conductive cloth portion.

Embodiment 62. The smart scale system of embodiment 60 or 61, wherein the plurality of electrodes comprises a first pair of electrodes forming a first closed circuit with the user.

Embodiment 63. The smart scale system of embodiment 62, wherein the first pair of electrodes is configured to contact the user's first foot.

Embodiment 64. The first pair of electrodes is coupled to the bioelectrical impedance module of the bioelectrical impedance system, and the first pair of electrodes is configured to measure the current in the first closed circuit and generate current data. , The smart scale system of embodiment 62 or 63.

Embodiment 65. One smart scale of any one of embodiments 62-64, further comprising a second pair of electrodes configured such that the plurality of electrodes are in conductive contact with the user to form a second closed circuit with the user. system.

Embodiment 66. The smart scale system of embodiment 65, wherein the second pair of electrodes is configured to contact the user's second foot.

Embodiment 67. The smart scale system of embodiment 65 or 66, wherein the second pair of electrodes is configured to measure the voltage of the second closed circuit and generate voltage data.

Embodiment 68.1 One or more processors
Determining that a portion of the user is in contact with the smart scale system, at least in part, based on weight data, pressure data, or both.
Executes a machine-readable instruction to activate and perform a camera configured to generate the user's image data, at least in part, based on the determination that a portion of the user is in contact with the smart scale system. The smart scale system of any one of embodiments 36-67, further configured to.

Embodiment 69.1 One or more processors
Embodiments further configured to execute machine-readable instructions to ensure that a user is an unregistered user of a smart scale system, at least in part, based on image data and registered user data. 68 smart scale systems

Embodiment 70. 1 or more processors
Determining the user's load cell weight based on the weight data received,
Displaying the load cell weight on the display device as the user's actual weight, at least in part, based on the fact that the load cell weight does not exceed a predetermined threshold.
Estimating the weight of the user's pressure sensor, at least partially based on the determination that the weight of the load cell exceeds a predetermined threshold, and (i) at least partially based on the received pressure data, and (ii). ) The smart of any one of embodiments 36-69, further configured to display the weight of the pressure sensor on the display device as the user's actual weight and to execute machine-readable instructions to do so. Scale system.

Embodiment 71. One or more processors
Determining the user's load cell weight based on the weight data received,
Receiving the user's load cell weight as input to the machine learning algorithm,
The smart scale of any one of embodiments 36-70, further configured to generate a user's normalized weight as output of a machine learning algorithm and to execute machine-readable instructions to do so. system.

Embodiment 72. Machine learning algorithms, as input, (i) whether the user is dressed or undressed, (ii) the user's recent shower usage, (iii) the user last ate and / or drank. The smart scale system of embodiment 71, further receiving adjustment reasons including time, (iv) the type of food of the user's last meal, (v) the state of the shower, or (vi) any combination thereof.

Embodiment 73.1 One or more processors
Embodiment 72 further configured to perform machine-readable instructions on the display device to display the user's load cell weight, the user's normalized weight, the reason for adjustment, or any combination thereof. Smart scale system.

Embodiment 74.1 One or more processors
Receiving past data, wherein the past data includes past load cell weight data and past normalized weight data.
One of the smart scale systems of embodiments 71-73, which is further configured to use the received historical data to train machine learning algorithms and to execute machine-readable instructions to do so. ..

Embodiment 75. The smart scale system of embodiment 74, in which historical data is associated with other users.

Embodiment 76. The smart scale system of embodiment 74 or 75, wherein historical data is associated with a user of the smart scale system.

Embodiment 77.1 One or more processors
Determining a user's estimated body composition, at least in part, based on bioelectrical impedance data, performing machine-readable instructions to determine that the estimated body composition includes body fat and muscle mass. The smart scale system according to any one of embodiments 60 to 76, which is further configured as described above.

Embodiment 78.1 One or more processors
Any one of embodiments 36-77, further configured to perform machine-readable instructions to perform generating pressure heatmaps associated with the user, at least in part based on pressure data. Smart scale system.

Embodiment 79. The smart scale system of embodiment 78, wherein the pressure heat map represents the pressure gradient associated with the user's foot and shows the user's weight distribution.

80.1 or more processors
One of the smarts of embodiments 36-79, further configured to perform machine-readable instructions to perform calculations on the length of the user's foot, at least partially based on pressure data. Scale system.

Embodiment 81.1 One or more processors
The smart scale system of Embodiment 80, which is further configured to perform machine-readable instructions to make estimates of the user's shoe size, at least in part, based on the calculated foot length. ..

Embodiment 82.1 One or more processors
The smart scale system of any one of embodiments 36-81, further configured to perform machine-readable instructions for determining a user's foot profile, at least in part based on pressure data.

Embodiment 83. The smart scale system of Embodiment 82, wherein the profile of the foot comprises a choice from high arc, low arc, and medium arc.

Embodiment 84.1 One or more processors
The smart scale system of embodiment 83, further configured to perform machine-readable instructions to determine a user's insole profile, at least in part, based on pressure data.

Embodiment 85.1 One or more processors
Any of embodiments 78-84, which are further configured to perform machine-readable instructions to perform detection of whether a user has a diabetic foot, at least partially based on pressure data. One smart scale system.

Embodiment 86. The smart scale system of any one of embodiments 36-85, wherein the memory and control system is coupled to the first side of the substrate.

Embodiment 87. The smart scale system according to any one of embodiments 36 to 86, wherein the display device is associated with a second user who is a registered user of the smart scale system.

Embodiment 88. Further including a communication network coupled to the control system, the communication network includes a Bluetooth network, a Wi-Fi network, or both, and the communication network is configured to couple the control system to one or more electronic devices. The smart scale system according to any one of the embodiments 36 to 87.

Embodiment 89. The smart scale system of Embodiment 88, wherein one or more electronic devices include a display device.

Embodiment 90. It ’s a smart scale system.
With the board
Multiple load cells coupled to the first side of the board, configured to generate weight data associated with the user, and
An array of pressure sensors coupled to a second opposite side of the substrate, the array of pressure sensors configured to generate pressure data associated with the user.
Memory for storing registered user data and machine-readable instructions,
A control system that is coupled to memory
Receiving weight data from multiple load cells and
Receiving pressure data from an array of pressure sensors,
Determining that a user is a registered user of a smart scale system, at least in part, based on pressure data and registered user data.
One or more processors configured to display a prompt on the display device to enter information associated with the weight data received by the user and to perform machine-readable instructions to do so. A smart scale system, including a control system, which is arranged to provide a control signal.

Embodiment 91.1 One or more processors
Receiving user information at the prompt and
Embodiments further configured to modify weight data to output normalized weights, at least in part, based on received user information, and to execute machine-readable instructions to do so. 90 smart scale system.

Embodiment 92. One or more processors
The smart scale system of embodiment 91, further configured to perform machine-readable instructions for the modified weight data to be displayed on a display device.

Embodiment 93. User information includes (i) whether the user is dressed or undressed, (ii) the user's recent toilet usage, (iii) the last time the user ate and / or drank, (iv). The smart scale system of embodiment 91 or 92, comprising: the type of food of the user's last meal, (v) the state of the shower, or (vi) any combination thereof.

Embodiment 94. One or more processors
Determining the user's load cell weight based on the weight data received,
Receiving the user's load cell weight as input to the machine learning algorithm,
The smart scale of any one of embodiments 91-93, further configured to generate a user's normalized weight as output of a machine learning algorithm and to execute machine-readable instructions to do so. system.

Embodiment 95. One or more processors
Receiving past data, wherein the past data includes past weight data, past user information, and past normalized weight data.
The smart scale system of any one of embodiments 90-94, further configured to use the received historical data to train machine learning algorithms and to execute machine-readable instructions to do so. ..

Embodiment 96. A method for determining a user's normalized weight,
Receiving registered user data from the memory of a smart scale system, the registered user data including past weight data, past user information, and past normalized weight data.
Using past weight data, past user information, and past normalized weight data to train machine learning algorithms,
Receiving pressure data associated with the user from an array of pressure sensors in a smart scale system,
Receiving the current weight data associated with the user from multiple load cells in the smart scale system,
Determining that a user is a registered user of a smart scale system, at least in part, based on pressure data and registered user data.
To display a prompt on the display device to prompt the user to enter the information associated with the current weight data.
Receiving current user information at the prompt,
Receiving the current weight data and current user information associated with the user as input to the machine learning algorithm,
A method, including generating a user's normalized weight as the output of a machine learning algorithm.

One or more elements or embodiments or steps from any one of embodiments 1-96 and / or any one or more of claims 1-40 below, or any portion thereof, is otherwise. One or more elements or embodiments or steps from one or more of any of embodiments 1-96 and / or any of claims 1-40, or combinations thereof, or any portion thereof. In combination with, one or more additional embodiments and / or claims of the present disclosure can be formed.

CONCLUSIONS Various operations of the exemplary methods described herein can be performed by algorithms, at least in part. The algorithm may be included in a program code or instruction stored in memory (eg, the non-temporary computer-readable storage medium described above). Such algorithms may include machine learning algorithms. In some embodiments, machine learning algorithms cannot explicitly program a computer to perform a function, but can learn from training data to create predictive models that perform the function.

The various operations of the exemplary methods described herein are at least partially configured by one or more processors that are temporarily (eg, by software) or permanently configured to perform the associated operation. Can be executed. Whether temporarily or permanently configured, such a processor may configure a processor-mounted engine that operates to perform one or more of the operations or functions described herein.

Similarly, the methods described herein can be implemented, at least in part, in a processor, where a particular processor or multiple processors are examples of hardware. For example, at least some of the operations of the method can be performed by one or more processors or processor implementation engines. In addition, one or more processors may operate to support the performance of related operations in a "cloud computing" environment or "software as a service" (Software as a Service). For example, at least some of the operations can be performed by a group of computers (as an example of a machine containing a processor), and these operations are over a network (eg, the Internet) and one or more suitable. It can be accessed through an interface (eg, an application program interface (API)).

Some performance of the operation can be distributed not only within a single machine, but also among processors deployed on multiple machines. In some exemplary embodiments, the processor or processor-implemented engine may be located in a single geographic location (eg, in a home environment, office environment, or server farm). In another exemplary embodiment, the processor or processor implementation engine may be distributed over several geographic locations.

The subject matter has been described with reference to specific exemplary embodiments, but various modifications and changes to these embodiments are made without departing from the broader scope of the embodiments of the present disclosure. It can be carried out. Such embodiments of the subject matter are hereby voluntarily limiting the scope of the application to any single disclosure or concept, provided herein solely for convenience and when the plurality are actually disclosed. Can be referred to individually or collectively by the term "invention" without the intent of.

The embodiments presented herein are described in sufficient detail to allow one of ordinary skill in the art to practice the disclosed teachings. Other embodiments may be used and derived so that structural and logical substitutions and modifications can be made without departing from the scope of the present disclosure. Therefore, the detailed description should not be construed in a limited sense, and the scope of the various embodiments, along with the full range of equivalents to which such claims are entitled, of the attached patent claims. It is defined only by the range.

Any process description, element, or block in the flow diagram described and / or shown in the accompanying figures herein is one or more executable instructions for implementing a particular logical function or step in the process. It should be understood as a potential representation of a module, segment, or portion of code that contains. Alternative implementations are included within the scope of the embodiments described herein, and the elements or functions are, as will be understood by those of skill in the art, substantially simultaneously or vice versa, depending on the relevant function. Can be removed and implemented in no particular order from those shown or considered, including.

As used herein, the term "or" may be construed in either a comprehensive or exclusive sense. In addition, multiple instances may be provided for the resources, behaviors, or structures described herein as a single instance. Moreover, the boundaries between various resources, behaviors, engines, and data stores are somewhat arbitrary, and certain behaviors are shown in the context of certain exemplary configurations. Other assignments of functionality are envisioned and may be included within the scope of the various embodiments of the present disclosure. In general, structures and functions presented as separate resources in an exemplary configuration can be implemented as combined structures or resources. Similarly, structures and functions presented as a single resource can be implemented as separate resources. These and other modifications, modifications, additions, and improvements fall within the scope of the embodiments of the present disclosure, as represented by the appended claims. Therefore, the specification and drawings should be viewed in an exemplary sense, not in a limiting sense.

Unless otherwise stated or understood in the context in which they are used, conditional terms such as "can", "cold", "might", "may" are generally used. It is intended to convey that a particular embodiment comprises a particular feature, element, and / or step and does not include another embodiment. Thus, such conditional terms are that features, elements, and / or steps are somehow required for one or more embodiments, or that one or more embodiments are these features, elements. , And / or generally include logic to determine whether a step is included in or executed in any particular embodiment, with or without user input or prompt. Not intended to suggest.

Although this disclosure has been described with reference to one or more particular embodiments or implementations, one of ordinary skill in the art recognizes that numerous changes may be made without departing from the spirit and scope of the disclosure. Will do. Each of these embodiments and implementations and their obvious variations is conceivable as being within the spirit and scope of the present disclosure described in the claims below.

Claims (28)

A method for determining the normalized weight of a non-static item,
Receiving weight data associated with the non-static item from multiple load cells,
Determining the load cell weight of the non-static item, at least in part, based on the weight data.
Receiving the load cell weight of the non-static item as input to the machine learning algorithm,
Receiving pressure data associated with the non-static item from an array of pressure sensors
Generating a pressure heatmap that represents the pressure gradient associated with the non-static item and shows the weight distribution of the non-static item, at least in part based on the pressure data.
To generate the normalized weight of the non-static item as output to the machine learning algorithm,
A method characterized by including. Receiving the past data associated with the non-static item, wherein the past data includes past load cell weight data and past normalized weight data.
Using the historical data to train the machine learning algorithm,
The method according to claim 1, further comprising. The historical data is associated with other non-static items in the same category,
The method according to claim 2 , wherein the method is characterized by the above. The historical data is associated with the non-static item of the smart scale system, and the smart scale system includes the plurality of load cells.
The method according to claim 2 , wherein the method is characterized by the above. The plurality of load cells are configured to generate the weight data according to the non-static item involved in the smart scale system.
The smart scale system includes the plurality of load cells.
The method according to claim 1, wherein the method is characterized by the above. The non-static item involved in the smart scale system moves over (i) the non-static item standing on the cover layer of the smart scale system, and (ii) the cover layer of the smart scale system. Including target item or (iii) both,
The method according to claim 5 , wherein the method is characterized by the above. The array of pressure sensors is configured to generate the pressure data in response to the non-static items involved in the smart scale system.
The smart scale system comprises an array of pressure sensors.
The method according to claim 1 , wherein the method is characterized by the above. The pressure heat map represents the foot of the non-static item or the pressure gradient associated with the foot and shows the weight distribution of the non-static item.
The method according to claim 1 , wherein the method is characterized by the above. The array of pressure sensors is coupled to the mattress of the non-static item.
The above method
Receiving the pressure data from the array of pressure sensors during a sleep session of the non-static item.
Determining the sleep state of the non-static item, at least in part, based on the pressure data of the non-static item during the sleep session.
The method according to claim 1 , further comprising. The sleep state of the non-static item includes (i) whether the non-static item has a sleep disorder, (ii) the sleep quality of the non-static item, or (iii) both.
The method according to claim 9 , wherein the method is characterized by the above. Receiving the weight data of the non-static item during the sleep session from the plurality of load cells.
Determining a change in the weight of the non-static item during the sleep session, at least in part, based on the weight data of the non-static item during the sleep session.
9. The method of claim 9 , further comprising. It ’s a smart scale system.
Multiple load cells coupled to the first side of the board, configured to generate weight data associated with non-static items.
A control system that includes one or more processors,
With a memory with stored machine-readable instructions,
The first aspect of the invention is when the control system is coupled to the memory and the machine-readable instructions in the memory are executed by at least one of the one or more processors of the control system. The method described is carried out,
A smart scale system featuring that. With more cover layer,
The smart scale system according to claim 12 . The cover layer comprises a sheet of cloth.
13. The smart scale system according to claim 13 . The cloth sheet comprises at least two conductive cloth portions separated from each other.
The smart scale system according to claim 14 . The at least two conductive fabric portions are at least 3 inches apart from each other.
The smart scale system according to claim 15 . The substrate is one or more pieces of glass.
The smart scale system according to claim 12 . The plurality of load cells include a 4 × 4 array of load cells.
A 4x4 array of load cells is coupled to an analog-to-digital converter.
The smart scale system according to claim 12 . The plurality of load cells include at least four single load cells.
Each of the four single load cells is coupled to their respective analog-to-digital converter.
The smart scale system according to claim 12 . Further comprising an array of pressure sensors coupled to the second opposite side of the substrate.
The array of pressure sensors is configured to generate pressure data associated with the non-static item.
The smart scale system according to claim 12 . The array of pressure sensors comprises a first sheet and a second sheet.
The smart scale system according to claim 20 . The first sheet comprises a pressure sensitive sheet positioned adjacent to the second sheet.
21. The smart scale system according to claim 21 . The pressure sensitive sheet comprises a piezo resistance sheet configured to change its electrical resistance in response to the pressure applied to it.
22. The smart scale system according to claim 22 . The second sheet contains a plurality of conductive trace patterns.
21. The smart scale system according to claim 21 . Each of the plurality of conductive trace patterns defines a pressure sensor in an array of pressure sensors.
24. The smart scale system according to claim 24 . Each of the plurality of conductive trace patterns includes an inner disk and an outer ring.
24. The smart scale system according to claim 24 . The outer ring is an equilateral polygon or a perfect circle.
26. The smart scale system according to claim 26 . The memory and the control system are coupled to the first side of the substrate.
The smart scale system according to claim 12 .

Images